© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-RES-MATRYOSHKA-DC
    7. 1234
    Prev
    Next
    INDEX
    Explanations

    Lithuanian words within a historical context, possibly related to WWII

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.24.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    chanind/pile-uncopyrighted-gemma-1024-abbrv-1B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wicidata
    -0.57
     och
    -0.55
     Roskov
    -0.54
     för
    -0.50
    nossa
    -0.50
    ända
    -0.48
    tiskt
    -0.47
     壓
    -0.47
    ligheter
    -0.47
    änien
    -0.46
    POSITIVE LOGITS
     til
    0.51
    hésite
    0.43
    aryti
    0.43
     mere
    0.41
     here
    0.41
    erne
    0.41
     selv
    0.40
     over
    0.40
    vej
    0.40
     Câmara
    0.40
    Activations Density 0.048%

    No Known Activations